# An adaptive music generation architecture for games based on the deep learning Transformer mode

arXiv: https://arxiv.org/abs/2207.01698 · HTML: https://mlsanity.com/paper/2207.01698/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 50 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [Onsets and Frames: Dual-Objective Piano Transcription](https://mlsanity.com/paper/1710.11153/) (2017)
- [From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends](https://mlsanity.com/paper/2004.03586/) (2020)
- [Adaptive Music Composition for Games](https://mlsanity.com/paper/1907.01154/) (2019)
- [Interactive Music Generation with Positional Constraints using Anticipation-RNNs](https://mlsanity.com/paper/1709.06404/) (2017)
- [Interactive Music and Synchronous Reactive Programming](https://mlsanity.com/paper/2006.03102/) (2020)

## Built on by (most cited first, 3 of 3)

- [Motifs, Phrases, and Beyond: The Modelling of Structure in Symbolic Music Generation](https://mlsanity.com/paper/2403.07995/) (2024)
- [SpellForger: Prompting Custom Spell Properties In-Game using BERT supervised-trained model](https://mlsanity.com/paper/2511.16018/) (2025)
- [A novel LSTM music generator based on the fractional time-frequency feature extraction](https://mlsanity.com/paper/2604.17823/) (2026)

## Abstract (arXiv)

This paper presents an architecture for generating music for video games based on the Transformer deep learning model. Our motivation is to be able to customize the generation according to the taste of the player, who can select a corpus of training examples, corresponding to his preferred musical style. The system generates various musical layers, following the standard layering strategy currently used by composers designing video game music. To adapt the music generated to the game play and to the player(s) situation, we are using an arousal-valence model of emotions, in order to control the selection of musical layers. We discuss current limitations and prospects for the future, such as collaborative and interactive control of the musical components.